arc-world-engine-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ARC_API_KEY | No | API key required to access a real public ARC environment. | |
| ARC_WORLD_MCP_TRANSPORT | No | Set to 'streamable-http' for an HTTP transport. Defaults to stdio. | stdio |
Capabilities
Features and capabilities supported by this server
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| create_worldB | Create an empty deterministic world using raw ARC colors 0-15. |
| load_static_mapA | Replace the static color and collision layers without creating actors. |
| set_viewportC | Set the integer camera origin and viewport, up to 64 by 64 cells. |
| create_actorC | Create a generic actor; cells are [local_x, local_y, optional_color]. |
| update_actorC | Update only the provided generic actor state and transform fields. |
| remove_actorA | Delete an actor and automatically remove ECE rules that reference it. |
| split_actorC | Split one actor by partitioning all of its local topology cells. |
| merge_actorsC | Merge actors into the first ID using their rendered world topology. |
| add_directional_movementC | Bind ACTION1-4 to up/down/left/right movement for an actor. |
| add_ruleB | Attach actor ECE code. Use actor.value predicates and frame N effects. condition_code supports and/or, for example:
|
| add_collision_effectB | Apply an effect when one actor collides with another actor or static map. |
| add_click_effectC | Apply an effect when ACTION6 clicks the source actor. |
| add_timer_effectC | Apply an actor effect on discrete action ticks, not wall-clock time. |
| simulate_actionB | Advance one deterministic turn; ACTION6 uses viewport click coordinates. |
| compare_observationB | Compare a real ARC frame against the model's current rendered viewport. |
| create_snapshotB | Clone the complete native world for later rollback. |
| rollbackB | Restore a previously named native snapshot. |
| get_world_stateA | Return rendered layers, actors, rules, hashes, trace, and debug history. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| current_world_resource | Complete current world model as JSON. |
| current_frame_resource | Current predicted ARC frame as JSON. |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/junxiangyang0707-hash/arc-agi-3-world-model-lab'
If you have feedback or need assistance with the MCP directory API, please join our Discord server